Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
universal-workflow-init
Bootstraps new projects by running a 5-question intake and generating a minimal scaffold (WORKPLAN.md, BRIEF.md, OUTLINE.md, SOURCES.md, LOG.md) plus optional folders for writing/research/coding. Use when the user asks to start a new project, plan a workflow, scaffold folders/files, or set up a reusable pipeline.
majiayu000/claude-skill-registry 163
-
clarification-expert
Clarify ambiguous requests by researching first, then asking only judgment calls; stop before implementation.
majiayu000/claude-skill-registry 163
-
prompt-engineering
Expert prompt optimization system for building production-ready AI features. Use when users request help improving prompts, want to create system prompts, need prompt review/critique, ask for prompt optimization strategies, want to analyze prompt effectiveness, mention prompt engineering best practices, request prompt templates, or need guidance on structuring AI instructions. Also use when users provide prompts and want suggestions for improvement.
majiayu000/claude-skill-registry 163
-
requirement-extraction
Extract structured requirements with REQ-* keys from raw intent. Transforms vague user intent into formal requirements with unique keys, acceptance criteria, and business context. Use when starting new features or analyzing user stories.
majiayu000/claude-skill-registry 163
-
dependency-evaluator
Evaluates whether a programming language dependency should be used by analyzing maintenance activity, security posture, community health, documentation quality, dependency footprint, production adoption, license compatibility, API stability, and funding sustainability. Use when users ask "should I use X or Y?", "are there better options for [feature]?", "what's a good library for [task]?", "how do we feel about [dependency]?", or when considering adding a new dependency, evaluating an existing dependency, or comparing/evaluating package alternatives.
majiayu000/claude-skill-registry 163
-
Observability Instrumentation
Comprehensive observability methodology implementing three pillars (logs, metrics, traces) with structured logging using Go slog, Prometheus-style metrics, and distributed tracing patterns. Use when adding observability from scratch, logs unstructured or inadequate, no metrics collection, debugging production issues difficult, or need performance monitoring. Provides structured logging patterns (contextual logging, log levels DEBUG/INFO/WARN/ERROR, request ID propagation), metrics instrumentation (counter/gauge/histogram patterns, Prometheus exposition), tracing setup (span creation, context propagation, sampling strategies), and Go slog best practices (JSON formatting, attribute management, handler configuration). Validated in meta-cc with 23-46x speedup vs ad-hoc logging, 90-95% transferability across languages (slog specific to Go but patterns universal).
majiayu000/claude-skill-registry 163
-
dependency-evaluator
Evaluates whether a programming language dependency should be used by analyzing maintenance activity, security posture, community health, documentation quality, dependency footprint, production adoption, license compatibility, API stability, and funding sustainability. Use when users ask "should I use X or Y?", "are there better options for [feature]?", "what's a good library for [task]?", "how do we feel about [dependency]?", or when considering adding a new dependency, evaluating an existing dependency, or comparing/evaluating package alternatives.
majiayu000/claude-skill-registry 163
-
hubspot-list-calls
List call engagements from HubSpot CRM. Load when user says 'list calls', 'show calls', 'call history', 'hubspot calls'. Returns logged call records.
majiayu000/claude-skill-registry 163
-
voltage-park
Provision and manage Voltage Park H100 GPU instances. Use when the user needs to spin up H100s, SSH into VP instances, transfer files, or terminate cloud GPU instances.
majiayu000/claude-skill-registry 163
-
joy-delight
Use when creating animations that evoke happiness, surprise, or delightful moments in the user experience.
majiayu000/claude-skill-registry 163
-
implementation-checkpoint
Generate standardized checkpoint reports for multi-phase implementation projects. This skill should be used when pausing implementation at strategic milestones (phase completion, user story completion, critical features) to create comprehensive progress reports with task breakdowns, metrics, knowledge base entries, and resume instructions.
majiayu000/claude-skill-registry 163
-
prp-workflow
Comprehensive PRP (Product Requirements Prompt) workflow for feature implementation. Use when user wants to implement complex features, needs a structured implementation plan, or mentions PRPs, feature implementation, or systematic development. Handles PRP generation from requirements, clarification of ambiguities, and execution for implementation. Three modes - Generation (create PRP), Clarification (resolve ambiguities), Execution (implement feature).
majiayu000/claude-skill-registry 163
-
windsurf-keyboard-shortcuts
Configure custom keyboard shortcuts for Cascade and AI features. Activate when users mention
"keyboard shortcuts", "keybindings", "hotkeys", "shortcut configuration",
or "customize shortcuts". Handles keybinding setup and optimization. Use when working with windsurf keyboard shortcuts functionality. Trigger with phrases like "windsurf keyboard shortcuts", "windsurf shortcuts", "windsurf".
majiayu000/claude-skill-registry 163
-
software-demonstration-script
Generate compelling demo walkthrough scripts that highlight key features, create "wow moments", handle objections, and transition smoothly to closing the $15K+ sale.
majiayu000/claude-skill-registry 163
-
Market Research and Competitive Analysis
TAM/SAM/SOM calculation, competitor analysis, and market trends identification. Use when analyzing markets, validating business ideas, or entering new markets.
majiayu000/claude-skill-registry 163
-
windsurf-extension-pack
Install and configure essential Windsurf extensions for productivity. Activate when users mention
"install extensions", "setup windsurf plugins", "configure extensions", "extension recommendations",
or "productivity extensions". Handles extension installation and configuration. Use when working with windsurf extension pack functionality. Trigger with phrases like "windsurf extension pack", "windsurf pack", "windsurf".
majiayu000/claude-skill-registry 163
-
MCP Configuration
MCP server configuration templates and setup scripts. Use when configuring MCP servers, setting up MCP environment, managing MCP configs, adding MCP servers, or when user mentions MCP setup, MCP configuration, server environment, or MCP installation.
majiayu000/claude-skill-registry 163
-
multiplex-imaging-analysis
Optimizing segmentation feature extraction, SOM clustering, and spatial analysis for multiplex immunofluorescence imaging with cell compartment and ECM features
majiayu000/claude-skill-registry 163
-
resolve-pr-feedback
Check a PR for unresolved automated review feedback (Copilot, CodeRabbit) and invoke the appropriate resolver skills. Use when the user says "resolve PR feedback", "check PR comments", "address review comments", or wants to handle all automated review feedback on a PR.
majiayu000/claude-skill-registry 163
-
maintaining-changelog
Updates or creates CHANGELOG.md files for pull request changes. Use when users request changelog updates, or when adding entries for new features, fixes, or breaking changes.
majiayu000/claude-skill-registry 163
-
user-feedback-clarity
Use when users don't notice feedback, miss state changes, or can't tell if their action worked
majiayu000/claude-skill-registry 163
-
drafting-innovation-prd-one-pagers
Generate tight, one-page PRDs for CustomGPT.ai Labs projects aligned to Why/How/What, success metrics, and fast experimentation constraints.
majiayu000/claude-skill-registry 163
-
changelog-skill
Use after completing user-visible features, fixes, or behavior changes - NOT for internal docs (CLAUDE.md, DECISIONS.md, _tasks/)
majiayu000/claude-skill-registry 163
-
Game Sprint Planner
Plan development sprints for Stapledons Voyage game features. Analyzes design docs, estimates effort considering AILANG constraints, and creates realistic sprint plans. Use when user asks to "plan sprint" or estimate game feature timelines.
majiayu000/claude-skill-registry 163